393 lines
13 KiB
C++
393 lines
13 KiB
C++
/*=========================================================================
|
|
|
|
Program: KWSys - Kitware System Library
|
|
Module: $RCSfile$
|
|
|
|
Copyright (c) Kitware, Inc., Insight Consortium. All rights reserved.
|
|
See Copyright.txt or http://www.kitware.com/Copyright.htm for details.
|
|
|
|
This software is distributed WITHOUT ANY WARRANTY; without even
|
|
the implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR
|
|
PURPOSE. See the above copyright notices for more information.
|
|
|
|
=========================================================================*/
|
|
// Original Copyright notice:
|
|
// Copyright (C) 1991 Texas Instruments Incorporated.
|
|
//
|
|
// Permission is granted to any individual or institution to use, copy, modify,
|
|
// and distribute this software, provided that this complete copyright and
|
|
// permission notice is maintained, intact, in all copies and supporting
|
|
// documentation.
|
|
//
|
|
// Texas Instruments Incorporated provides this software "as is" without
|
|
// express or implied warranty.
|
|
//
|
|
// Created: MNF 06/13/89 Initial Design and Implementation
|
|
// Updated: LGO 08/09/89 Inherit from Generic
|
|
// Updated: MBN 09/07/89 Added conditional exception handling
|
|
// Updated: MBN 12/15/89 Sprinkled "const" qualifiers all over the place!
|
|
// Updated: DLS 03/22/91 New lite version
|
|
//
|
|
|
|
#ifndef @KWSYS_NAMESPACE@_RegularExpression_hxx
|
|
#define @KWSYS_NAMESPACE@_RegularExpression_hxx
|
|
|
|
#include <@KWSYS_NAMESPACE@/Configure.h>
|
|
#include <@KWSYS_NAMESPACE@/Configure.hxx>
|
|
|
|
#include <@KWSYS_NAMESPACE@/std/string>
|
|
|
|
/* Define this macro temporarily to keep the code readable. */
|
|
#if !defined (KWSYS_NAMESPACE) && !defined(@KWSYS_NAMESPACE@_NAME_IS_KWSYS)
|
|
# define kwsys_std @KWSYS_NAMESPACE@_std
|
|
#endif
|
|
|
|
namespace @KWSYS_NAMESPACE@
|
|
{
|
|
|
|
/** \class RegularExpression
|
|
* \brief Implements pattern matching with regular expressions.
|
|
*
|
|
* This is the header file for the regular expression class. An object of
|
|
* this class contains a regular expression, in a special "compiled" format.
|
|
* This compiled format consists of several slots all kept as the objects
|
|
* private data. The RegularExpression class provides a convenient way to
|
|
* represent regular expressions. It makes it easy to search for the same
|
|
* regular expression in many different strings without having to compile a
|
|
* string to regular expression format more than necessary.
|
|
*
|
|
* This class implements pattern matching via regular expressions.
|
|
* A regular expression allows a programmer to specify complex
|
|
* patterns that can be searched for and matched against the
|
|
* character string of a string object. In its simplest form, a
|
|
* regular expression is a sequence of characters used to
|
|
* search for exact character matches. However, many times the
|
|
* exact sequence to be found is not known, or only a match at
|
|
* the beginning or end of a string is desired. The RegularExpression regu-
|
|
* lar expression class implements regular expression pattern
|
|
* matching as is found and implemented in many UNIX commands
|
|
* and utilities.
|
|
*
|
|
* Example: The perl code
|
|
*
|
|
* $filename =~ m"([a-z]+)\.cc";
|
|
* print $1;
|
|
*
|
|
* Is written as follows in C++
|
|
*
|
|
* RegularExpression re("([a-z]+)\\.cc");
|
|
* re.find(filename);
|
|
* cerr << re.match(1);
|
|
*
|
|
*
|
|
* The regular expression class provides a convenient mechanism
|
|
* for specifying and manipulating regular expressions. The
|
|
* regular expression object allows specification of such pat-
|
|
* terns by using the following regular expression metacharac-
|
|
* ters:
|
|
*
|
|
* ^ Matches at beginning of a line
|
|
*
|
|
* $ Matches at end of a line
|
|
*
|
|
* . Matches any single character
|
|
*
|
|
* [ ] Matches any character(s) inside the brackets
|
|
*
|
|
* [^ ] Matches any character(s) not inside the brackets
|
|
*
|
|
* - Matches any character in range on either side of a dash
|
|
*
|
|
* * Matches preceding pattern zero or more times
|
|
*
|
|
* + Matches preceding pattern one or more times
|
|
*
|
|
* ? Matches preceding pattern zero or once only
|
|
*
|
|
* () Saves a matched expression and uses it in a later match
|
|
*
|
|
* Note that more than one of these metacharacters can be used
|
|
* in a single regular expression in order to create complex
|
|
* search patterns. For example, the pattern [^ab1-9] says to
|
|
* match any character sequence that does not begin with the
|
|
* characters "ab" followed by numbers in the series one
|
|
* through nine.
|
|
*
|
|
* There are three constructors for RegularExpression. One just creates an
|
|
* empty RegularExpression object. Another creates a RegularExpression
|
|
* object and initializes it with a regular expression that is given in the
|
|
* form of a char*. The third takes a reference to a RegularExpression
|
|
* object as an argument and creates an object initialized with the
|
|
* information from the given RegularExpression object.
|
|
*
|
|
* The find member function finds the first occurence of the regualr
|
|
* expression of that object in the string given to find as an argument. Find
|
|
* returns a boolean, and if true, mutates the private data appropriately.
|
|
* Find sets pointers to the beginning and end of the thing last found, they
|
|
* are pointers into the actual string that was searched. The start and end
|
|
* member functions return indicies into the searched string that correspond
|
|
* to the beginning and end pointers respectively. The compile member
|
|
* function takes a char* and puts the compiled version of the char* argument
|
|
* into the object's private data fields. The == and != operators only check
|
|
* the to see if the compiled regular expression is the same, and the
|
|
* deep_equal functions also checks to see if the start and end pointers are
|
|
* the same. The is_valid function returns false if program is set to NULL,
|
|
* (i.e. there is no valid compiled exression). The set_invalid function sets
|
|
* the program to NULL (Warning: this deletes the compiled expression). The
|
|
* following examples may help clarify regular expression usage:
|
|
*
|
|
* * The regular expression "^hello" matches a "hello" only at the
|
|
* beginning of a line. It would match "hello there" but not "hi,
|
|
* hello there".
|
|
*
|
|
* * The regular expression "long$" matches a "long" only at the end
|
|
* of a line. It would match "so long\0", but not "long ago".
|
|
*
|
|
* * The regular expression "t..t..g" will match anything that has a
|
|
* "t" then any two characters, another "t", any two characters and
|
|
* then a "g". It will match "testing", or "test again" but would
|
|
* not match "toasting"
|
|
*
|
|
* * The regular expression "[1-9ab]" matches any number one through
|
|
* nine, and the characters "a" and "b". It would match "hello 1"
|
|
* or "begin", but would not match "no-match".
|
|
*
|
|
* * The regular expression "[^1-9ab]" matches any character that is
|
|
* not a number one through nine, or an "a" or "b". It would NOT
|
|
* match "hello 1" or "begin", but would match "no-match".
|
|
*
|
|
* * The regular expression "br* " matches something that begins with
|
|
* a "b", is followed by zero or more "r"s, and ends in a space. It
|
|
* would match "brrrrr ", and "b ", but would not match "brrh ".
|
|
*
|
|
* * The regular expression "br+ " matches something that begins with
|
|
* a "b", is followed by one or more "r"s, and ends in a space. It
|
|
* would match "brrrrr ", and "br ", but would not match "b " or
|
|
* "brrh ".
|
|
*
|
|
* * The regular expression "br? " matches something that begins with
|
|
* a "b", is followed by zero or one "r"s, and ends in a space. It
|
|
* would match "br ", and "b ", but would not match "brrrr " or
|
|
* "brrh ".
|
|
*
|
|
* * The regular expression "(..p)b" matches something ending with pb
|
|
* and beginning with whatever the two characters before the first p
|
|
* encounterd in the line were. It would find "repb" in "rep drepa
|
|
* qrepb". The regular expression "(..p)a" would find "repa qrepb"
|
|
* in "rep drepa qrepb"
|
|
*
|
|
* * The regular expression "d(..p)" matches something ending with p,
|
|
* beginning with d, and having two characters in between that are
|
|
* the same as the two characters before the first p encounterd in
|
|
* the line. It would match "drepa qrepb" in "rep drepa qrepb".
|
|
*
|
|
*/
|
|
class @KWSYS_NAMESPACE@_EXPORT RegularExpression
|
|
{
|
|
public:
|
|
/**
|
|
* Instantiate RegularExpression with program=NULL.
|
|
*/
|
|
inline RegularExpression ();
|
|
|
|
/**
|
|
* Instantiate RegularExpression with compiled char*.
|
|
*/
|
|
inline RegularExpression (char const*);
|
|
|
|
/**
|
|
* Instantiate RegularExpression as a copy of another regular expression.
|
|
*/
|
|
RegularExpression (RegularExpression const&);
|
|
|
|
/**
|
|
* Destructor.
|
|
*/
|
|
inline ~RegularExpression();
|
|
|
|
/**
|
|
* Compile a regular expression into internal code
|
|
* for later pattern matching.
|
|
*/
|
|
bool compile (char const*);
|
|
|
|
/**
|
|
* Matches the regular expression to the given string.
|
|
* Returns true if found, and sets start and end indexes accordingly.
|
|
*/
|
|
bool find (char const*);
|
|
|
|
/**
|
|
* Matches the regular expression to the given std string.
|
|
* Returns true if found, and sets start and end indexes accordingly.
|
|
*/
|
|
bool find (kwsys_std::string const&);
|
|
|
|
/**
|
|
* Index to start of first find.
|
|
*/
|
|
inline kwsys_std::string::size_type start() const;
|
|
|
|
/**
|
|
* Index to end of first find.
|
|
*/
|
|
inline kwsys_std::string::size_type end() const;
|
|
|
|
/**
|
|
* Returns true if two regular expressions have the same
|
|
* compiled program for pattern matching.
|
|
*/
|
|
bool operator== (RegularExpression const&) const;
|
|
|
|
/**
|
|
* Returns true if two regular expressions have different
|
|
* compiled program for pattern matching.
|
|
*/
|
|
inline bool operator!= (RegularExpression const&) const;
|
|
|
|
/**
|
|
* Returns true if have the same compiled regular expressions
|
|
* and the same start and end pointers.
|
|
*/
|
|
bool deep_equal (RegularExpression const&) const;
|
|
|
|
/**
|
|
* True if the compiled regexp is valid.
|
|
*/
|
|
inline bool is_valid() const;
|
|
|
|
/**
|
|
* Marks the regular expression as invalid.
|
|
*/
|
|
inline void set_invalid();
|
|
|
|
/**
|
|
* Destructor.
|
|
*/
|
|
// awf added
|
|
kwsys_std::string::size_type start(int n) const;
|
|
kwsys_std::string::size_type end(int n) const;
|
|
kwsys_std::string match(int n) const;
|
|
|
|
enum { NSUBEXP = 10 };
|
|
private:
|
|
const char* startp[NSUBEXP];
|
|
const char* endp[NSUBEXP];
|
|
char regstart; // Internal use only
|
|
char reganch; // Internal use only
|
|
const char* regmust; // Internal use only
|
|
int regmlen; // Internal use only
|
|
char* program;
|
|
int progsize;
|
|
const char* searchstring;
|
|
};
|
|
|
|
/**
|
|
* Create an empty regular expression.
|
|
*/
|
|
inline RegularExpression::RegularExpression ()
|
|
{
|
|
this->program = 0;
|
|
}
|
|
|
|
/**
|
|
* Creates a regular expression from string s, and
|
|
* compiles s.
|
|
*/
|
|
inline RegularExpression::RegularExpression (const char* s)
|
|
{
|
|
this->program = 0;
|
|
if ( s )
|
|
{
|
|
this->compile(s);
|
|
}
|
|
}
|
|
|
|
/**
|
|
* Destroys and frees space allocated for the regular expression.
|
|
*/
|
|
inline RegularExpression::~RegularExpression ()
|
|
{
|
|
//#ifndef WIN32
|
|
delete [] this->program;
|
|
//#endif
|
|
}
|
|
|
|
/**
|
|
* Set the start position for the regular expression.
|
|
*/
|
|
inline kwsys_std::string::size_type RegularExpression::start () const
|
|
{
|
|
return(this->startp[0] - searchstring);
|
|
}
|
|
|
|
|
|
/**
|
|
* Returns the start/end index of the last item found.
|
|
*/
|
|
inline kwsys_std::string::size_type RegularExpression::end () const
|
|
{
|
|
return(this->endp[0] - searchstring);
|
|
}
|
|
|
|
/**
|
|
* Returns true if two regular expressions have different
|
|
* compiled program for pattern matching.
|
|
*/
|
|
inline bool RegularExpression::operator!= (const RegularExpression& r) const
|
|
{
|
|
return(!(*this == r));
|
|
}
|
|
|
|
/**
|
|
* Returns true if a valid regular expression is compiled
|
|
* and ready for pattern matching.
|
|
*/
|
|
inline bool RegularExpression::is_valid () const
|
|
{
|
|
return (this->program != 0);
|
|
}
|
|
|
|
|
|
inline void RegularExpression::set_invalid ()
|
|
{
|
|
//#ifndef WIN32
|
|
delete [] this->program;
|
|
//#endif
|
|
this->program = 0;
|
|
}
|
|
|
|
/**
|
|
* Return start index of nth submatch. start(0) is the start of the full match.
|
|
*/
|
|
inline kwsys_std::string::size_type RegularExpression::start(int n) const
|
|
{
|
|
return this->startp[n] - searchstring;
|
|
}
|
|
|
|
|
|
/**
|
|
* Return end index of nth submatch. end(0) is the end of the full match.
|
|
*/
|
|
inline kwsys_std::string::size_type RegularExpression::end(int n) const
|
|
{
|
|
return this->endp[n] - searchstring;
|
|
}
|
|
|
|
/**
|
|
* Return nth submatch as a string.
|
|
*/
|
|
inline kwsys_std::string RegularExpression::match(int n) const
|
|
{
|
|
return kwsys_std::string(this->startp[n], this->endp[n] - this->startp[n]);
|
|
}
|
|
|
|
} // namespace @KWSYS_NAMESPACE@
|
|
|
|
/* Undefine temporary macro. */
|
|
#if !defined (KWSYS_NAMESPACE) && !defined(@KWSYS_NAMESPACE@_NAME_IS_KWSYS)
|
|
# undef kwsys_std
|
|
#endif
|
|
|
|
#endif
|